Deep Learning-Assisted Sensitive 3C-SiC Sensor for Long-Term Monitoring of Physical Respiration

Abstract

In human life, respiration serves as a crucial physiological signal. Continuous real-time respiration monitoring can provide valuable insights for the early detection and management of several respiratory diseases. High-sensitivity, noninvasive, comfortable, and long-term stable respiration devices are highly desirable. In spite of this, existing respiration sensors cannot provide continuous long-term monitoring due to the erosion from moisture, fluctuations in body temperature, and many other environmental factors. This research developed a wearable thermal-based respiration sensor made of cubic silicon carbide (3C-SiC) using a microfabrication process. The results showed that as a result of the Joule heating effect in the robustness 3C-SiC material, the sensor offered high sensitivity with the negative temperature coefficient of resistance of approximately 5,200ppmK^-1, an excellent response to respiration and long-term stability monitoring. Furthermore, by incorporating a deep learning model, this fabricated sensor can develop advanced capabilities to distinguish between the four distinct breath patterns: slow, normal, fast, and deep breathing, and provide an impressive classification accuracy rate of ≈ 99.7%. The results of this research represent a significant step in developing wearable respiration sensors for personal healthcare systems.